Skip to content
Blu SolutionsBlu Solutions
Guide

What people run on a Mac Studio — and why ours is bigger

Buy a Mac Studio for general local AI and the internet will point you at a ~27 billion parameter model. We run 176 billion — Qwen3.8-Flash-Next — on our own servers. Same family. Not the same league.

By the Blu Solutions team · Updated 21 November 2026 · General information, not advice for your specific situation.

If you asked local-AI people in 2026 what to run on a Mac Studio for general work — writing, coding, thinking, not a science project — the answer that keeps coming back is Qwen3.8-27B.

A 64 GB Studio owner measured that 27B at about 75 tokens per second with thinking left on. Unsloth calls it the strongest model for its size. Mac Studio testers pick it because a dense 70B often fits and then feels like a batch job. For everyday work, the 27B class is the one people actually recommend.

That is a good desktop model. It is not what we run for the firm.

What we run instead

We serve Qwen3.8-Flash-Next: 176 billion total parameters, 256K context, on our servers. You do not install it. You do not need the Studio. See Our AI.

Flash-Next is the checkpoint that does not live comfortably on a Mac. The 27B is the one that does. Ours is the bigger one. On Qwen’s own numbers, it is also the better one.

Qwen’s table — Flash-Next vs the Mac-class 27B

These are Qwen’s published scores, Flash-Next against Qwen3.8-27B. Higher is better. We did not run this bake-off in-house.

BenchmarkMac Studio pick (27B)Blu (Flash-Next, 176B)
LiveCodeBench v690.391.9
SWE-bench Pro61.762.5
SWE-bench Multilingual73.881.0
DeepSWE 1.142.258.7
NL2Repo-Bench42.348.1
CoWorkBench70.773.9
JobBench33.455.7

Flash-Next wins every row. DeepSWE (42.2 → 58.7) and JobBench (33.4 → 55.7) are not a rounding error. That is why we did not put a 27B under the desk and call it the office model.

For a client

A Mac Studio running 27B is a fine personal setup. An accounting firm’s working papers should not depend on whoever left LM Studio open. We host the 176B model, add our own RAG, and a person still approves the ledger. Data stays in the office.

Sources: Qwen Flash-Next model card (the table), Qwen3.8-27B, Unsloth on 27B, 64 GB Mac Studio measurements.

Where we can help

Questions we hear

What do people actually run on a Mac Studio for general work?

The usual recommendation in 2026 is Qwen3.8-27B — about 27 billion parameters. It is the dense model that fits, stays fast, and is what Mac Studio write-ups keep picking for everyday use. A 70B often fits on paper and then crawls.

Is Blu’s model the same thing?

No. We run Qwen3.8-Flash-Next: 176 billion total parameters, on our servers. Same publisher, much larger checkpoint. On Qwen’s published table it beats the 27B Mac-class model on every coding and agent score we list.

Do I need a Mac Studio to use you?

No. You apply as a client. We host the 176B model. A person still signs off anything that hits a ledger.

Keep the Studio for email. We keep the 176B model.

Apply for 1 March if you want the larger Qwen on our hardware — with a person on every figure.

CallWhatsAppApply for 1 March